CN107103615A - A kind of monitor video target lock-on tracing system and track lock method - Google Patents
A kind of monitor video target lock-on tracing system and track lock method Download PDFInfo
- Publication number
- CN107103615A CN107103615A CN201710217166.2A CN201710217166A CN107103615A CN 107103615 A CN107103615 A CN 107103615A CN 201710217166 A CN201710217166 A CN 201710217166A CN 107103615 A CN107103615 A CN 107103615A
- Authority
- CN
- China
- Prior art keywords
- target
- module
- lock
- video
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
- G06T7/251—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments involving models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/783—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
- G06F16/7837—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using objects detected or recognised in the video content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/7867—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, title and artist information, manually generated time, location and usage information, user ratings
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/254—Analysis of motion involving subtraction of images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20224—Image subtraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30232—Surveillance
Abstract
The invention discloses a kind of monitor video target lock-on tracing system, it is characterised in that including:Target image characteristics stuck-module, the characteristic information for obtaining target image sets up object module;Locking module is detected, target detection is carried out for the video image to input, locking needs the moving target followed the trail of;Tracing module, recognizes and follows the trail of the moving target;Target information analysis and arrangement module, the relevant information of lock onto target is gone out for analysis and arrangement;Data memory module, the relevant information for preserving the lock onto target that analysis and arrangement goes out, sets up database;As a result feedback module, for sending track lock object information to user.The monitor video target lock-on tracing system and track lock method of the present invention conveniently and efficiently needs user or target interested is picked out from monitor video, and intuitively reflect the movement locus of target, the time of artificial examination has been saved, the efficiency and accuracy of track lock is improved.
Description
Technical field
The present invention relates to computer information technology field, and in particular to a kind of monitor video target lock-on tracing system and lock
Determine method for tracing.
Background technology
With the progress of science and technology, the strategic propulsion of the developing of information technology, national " informationization " and smart city
Construction, the definition of video camera constantly rises, and cost is constantly reduced, and monitoring network has been dispersed throughout each corner of society, such as
Obtaining key message in the massive video information what is quickly and efficiently produced from monitoring network turns into urgent problem to be solved.Public security
Criminal policeman is usually requiring to scan for some specific objective in substantial amounts of monitor video during handling case, such as to violating
Guilty suspect and the search to vehicle, in traditional search procedure, to target be searched through human eye complete, it is necessary to
Substantial amounts of human resources, and degree of accuracy of its search can reduce with the degree of fatigue of people, therefore set up one kind and can search for automatically
The system of specific objective seems particularly significant in video.
Prior art is all in real time saved in video image all the time in the storage devices such as hard disk, video-tape, in case
Later retrieval, which returns to look into, waits application, but this larger memory space of needs.Although with the development of memory technology, the storage of Large Copacity
Equipment can preferably solve this problem, but in view of view data, which inherently has, takes the more defect of byte, therefore i.e.
It is the storage device that regardless of expense uses Large Copacity, it is also difficult to preserve all video images in longer period of time.
Prior art carry out Video content retrieval return look into when, it is many by the way of manually returning and looking into, namely adopt
With playing preserved video, and artificial judgment is carried out to video, look into mode inefficiency and easily slip for this time.People
Work is returned when looking into manually, and the speed of video playback can not be too fast, otherwise target object be likely to a sudden strain of a muscle i.e. without being noted, because
This section of 10 hours video, normal speed carries out back being accomplished by or so 10 hours if looking into from the beginning to the end, and is likely to
Significant video content only has several seconds or tens seconds, therefore efficiency is very low.And looked into for artificial return, Hui Cha
Personnel are watched during video for a long time, and notice can not keep concentrating for a long time, it is easy to fatigue be produced, so even being
Return and look into by normal speed, be also likely to appearance and slip and miss relevant information.For its shot using static camera
The video image that his application scenarios are obtained, there is also it is same the problem of.
The content of the invention
In view of the shortcomings of the prior art, the present invention provides a kind of monitor video target lock-on tracing system and track lock side
Method conveniently and efficiently needs user or target interested is picked out from monitor video, and intuitively reflects target
Movement locus, saved the time of artificial examination, improved the efficiency and accuracy of track lock, with higher practical valency
Value and widely application prospect.
The present invention solves technical problem and adopted the following technical scheme that:
The invention provides a kind of monitor video target lock-on tracing system, the monitor video target lock-on tracing system bag
Include:
Target image characteristics stuck-module, the characteristic information for obtaining target image sets up object module;
Locking module is detected, is connected with the target image characteristics stuck-module, target is carried out for the video image to input
Detection, locks the object for meeting the object module that the target image characteristics stuck-module is set up in the video image, that is, needs
The moving target to be followed the trail of;
Tracing module, is connected with the detection locking module, after the detection locking module captures the moving target, knows
Not and follow the trail of the moving target, return to inactive state until detecting the moving target, stop following the trail of the motion mesh
Mark;
Target information analysis and arrangement module, is connected with the tracing module, and the relevant information of lock onto target is gone out for analysis and arrangement,
Video image frame sequence information, the type of lock onto target, the characteristic information of lock onto target and locking including the lock onto target
The movable information of target;
Data memory module, with the target image characteristics stuck-module, target information analysis and arrangement module, tracing module, inspection
Survey locking module to be connected, the relevant information for preserving the lock onto target that analysis and arrangement goes out sets up database;
As a result feedback module, is connected with data memory module, for carrying out classification screening to the information in database, to reduce
The number of times that repeats of lock onto target relevant information described in continuous time section internal lock in the selection result, and by final object information
Send user to.
Preferably, the characteristic information of the target image includes:HSV color histograms feature, marginal point number and area
Ratio characteristic, perception Hash fingerprint characteristic.
Preferably, the video image frame sequence information includes video image temporal information and image frame identification.
Preferably, the system also includes the real-time display module of video, the real-time display module of video and the detection
Locking module is connected, for extracting one or more image, Huo Zheyi from video according to the video image frame sequence information
Section or multistage video, then show the image of extraction or play the video extracted in real time.
Present invention also offers a kind of monitor video target lock-on method for tracing, comprise the following steps:
(1)User inputs target image, and the characteristic information for extracting input picture sets up object module;
(2)Input video is read, and background model is set up according to the input video, to extract before the motion in each frame of video
Scape, and candidate target region is obtained by connected domain detection, asked in the candidate target region using the edge contour estimation technique
Go out all objects target frame position, wherein object target frame refers to the rectangle frame for including edge closure object;
(3)The characteristic similarity for having the object target frame of maximum comprehensive similarity with search target in candidate target region is made
For the corresponding similarity of candidate target region, it is somebody's turn to do if the comprehensive similarity of candidate target region and search target is more than threshold value locking
Target;
(4)Indicated to each containing the frame of video for following the trail of target, sort out its temporal information, the type of lock onto target, lock
The characteristic information and the movable information of lock onto target set the goal, and these information are stored, Put on file sets up database;
(5)Needed to contrast the information in database according to user, filter out and follow the trail of the number that target position information is changed
According to result is fed back to user by integration frame of video resource.
Preferably, the step(1)Middle background model uses mixed Gauss model.
Preferably, the step(2)In using the edge contour estimation technique obtain property in the candidate target region
Body target frame position comprises the following steps:A. the gradient map of target image is calculated;B. gradient map is subjected to multiple dimensioned scaling, obtained
Gradient map under different scale;C. the rectangle frame using yardstick as 4*4 travels through each gradient map, respectively from the square of the gradient map
Each pixel on shape frame four edges is set out with the direction perpendicular to the side, and calculating runs into first and is more than 64 Grad (i.e.
Marginal point) distance, if from each pixel on each side find marginal point distance average be less than 4, judge the square
The rectangle frame that shape frame corresponds to artwork by scaling is object target frame.
Preferably, user needs that by login account and password the retrieval system could be entered before input track lock target
System.
Compared with prior art, the present invention has following beneficial effect:
(1)The present invention monitor video target lock-on tracing system include target image characteristics stuck-module, detection locking module,
Tracing module, target information analysis and arrangement module, data memory module, result feedback module, can comprehensively extract target figure
The feature of picture, quickly in monitoring video flow track lock onto target, and carries out lasting tracking to it, and qualified frame of video is entered
Rower shows, information extraction and storage, and the storage area of saving, which accelerates video frequency searching by retrieving motion segments, significantly and returned, to be looked into
Speed, improve operating efficiency and retrieval rate, reduce wrong report and fail to report possibility, to the database of locking tracking target
Arrangement examination is carried out, the validity of information is further increased, high-quality locking tracking result can be fed back to user,
(2)The monitor video target lock-on method for tracing of the present invention sets up background model by mixed Gauss model, utilizes edge
The profile estimation technique obtains the characteristic similarity of all objects, more can fast and accurately lock onto target, improve the effect of track lock
Rate and accuracy, with widely application prospect.
Brief description of the drawings
By reading the detailed description made with reference to the following drawings to non-limiting example, further feature of the invention,
Objects and advantages will become more apparent upon:
Fig. 1 is a kind of monitor video target lock-on tracing system schematic diagram of the embodiment of the present invention 1;
Fig. 2 is a kind of monitor video target lock-on tracing system schematic diagram of the embodiment of the present invention 2;
Fig. 3 is the FB(flow block) of the monitor video target lock-on method for tracing of the embodiment of the present invention 2.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation is described, it is clear that described embodiment is only a part of embodiment of the invention, rather than whole embodiments.It is based on
Embodiment in the present invention, it is every other that those of ordinary skill in the art are obtained under the premise of creative work is not made
Embodiment, belongs to the scope of protection of the invention.
Embodiment 1.
As shown in figure 1, a kind of monitor video target lock-on tracing system of the present embodiment, including:Target image characteristics stent
Block 1, detection locking module 2, tracing module 3, target information analysis and arrangement module 4, data memory module 5, result feedback module
6。
Wherein target image characteristics stuck-module 1, object module, target are set up for obtaining the characteristic information of target image
The characteristic information of image includes:HSV color histograms feature, marginal point number and area ratio feature, perception Hash fingerprint are special
Levy;
Locking module 2 is detected, 1 is connected with the target image characteristics stuck-module, mesh is carried out for the video image to input
Mark detection, locks the object for meeting the object module that the target image characteristics stuck-module is set up in the video image, i.e.,
Need the moving target followed the trail of;
Tracing module 3, is connected 2 with the detection locking module, detects that locking module 2 captures the moving target described
Afterwards, recognize and follow the trail of the moving target, inactive state is returned to until detecting the moving target, stop following the trail of the fortune
Moving-target;
Target information analysis and arrangement module 4,3 are connected with the tracing module, and the related letter of lock onto target is gone out for analysis and arrangement
Breath, including the video image frame sequence information of the lock onto target, the type of lock onto target, the characteristic information and lock of lock onto target
The movable information set the goal, the video image frame sequence information includes video image temporal information and image frame identification;
Data memory module 5, with the target image characteristics stuck-module 1, target information analysis and arrangement module 2, tracing module
3rd, detection locking module connected 4, the relevant information for preserving the lock onto target that analysis and arrangement goes out sets up database;
As a result feedback module 6, are connected 5 with data memory module, for carrying out classification screening to the information in database, to reduce
The number of times that lock onto target relevant information described in continuous time section internal lock repeats in the selection result, and final result is believed
Breath sends user to.
The search method of the data retrieval system of the present embodiment, comprises the following steps:
(1)User inputs target image, and the characteristic information for extracting input picture sets up object module;
(2)Input video is read, and background model is set up according to the input video, to extract before the motion in each frame of video
Scape, and candidate target region is obtained by connected domain detection, asked in the candidate target region using the edge contour estimation technique
Go out all objects target frame position, wherein object target frame refers to the rectangle frame for including edge closure object;
(3)The characteristic similarity for having the object target frame of maximum comprehensive similarity with search target in candidate target region is made
For the corresponding similarity of candidate target region, it is somebody's turn to do if the comprehensive similarity of candidate target region and search target is more than threshold value locking
Target;
(4)Indicated to each containing the frame of video for following the trail of target, sort out its temporal information, the type of lock onto target, lock
The characteristic information and the movable information of lock onto target set the goal, and these information are stored, Put on file sets up database;
(5)Needed to contrast the information in database according to user, filter out and follow the trail of the number that target position information is changed
According to result is fed back to user by integration frame of video resource.
Embodiment 2.
As shown in Fig. 2 a kind of monitor video target lock-on tracing system of the present embodiment, including:Target image characteristics stent
Block 1, detection locking module 2, the real-time display module 3 of video, tracing module 4, target information analysis and arrangement module 5, data storage
Module 6, result feedback module 7.
Wherein target image characteristics stuck-module 1, object module, target are set up for obtaining the characteristic information of target image
The characteristic information of image includes:HSV color histograms feature, marginal point number and area ratio feature, perception Hash fingerprint are special
Levy;
Locking module 2 is detected, 1 is connected with the target image characteristics stuck-module, mesh is carried out for the video image to input
Mark detection, locks the object for meeting the object module that the target image characteristics stuck-module is set up in the video image, i.e.,
Need the moving target followed the trail of;
The real-time display module 3 of video, the real-time display module 3 of video is connected with the detection locking module 2, for according to institute
State video image frame sequence information and one or more image, or one or more snippets video are extracted from video, it is then aobvious in real time
The video for the image or broadcasting extraction extracted is shown;
Tracing module 4, is connected with the detection locking module 2, and the moving target is captured in the detection locking module 2
Afterwards, recognize and follow the trail of the moving target, inactive state is returned to until detecting the moving target, stop following the trail of the fortune
Moving-target;
Target information analysis and arrangement module 5,4 are connected with the tracing module, and the related letter of lock onto target is gone out for analysis and arrangement
Breath, including the video image frame sequence information of the lock onto target, the type of lock onto target, the characteristic information and lock of lock onto target
The movable information set the goal, the video image frame sequence information includes video image temporal information and image frame identification;
Data memory module 6, with the target image characteristics stuck-module 1, target information analysis and arrangement module 5, tracing module
4th, detection locking module 2 is connected, and the relevant information for preserving the lock onto target that analysis and arrangement goes out sets up database;
As a result feedback module 7, are connected with data memory module 6, for carrying out classification screening to the information in database, to reduce
The number of times that lock onto target relevant information described in continuous time section internal lock repeats in the selection result, and final result is believed
Breath sends user to.
As shown in figure 3, present invention also offers a kind of monitor video target lock-on method for tracing, comprising the following steps:
S1:User inputs user name and login password, into monitor video target lock-on tracing system;
S2:User inputs target image, and the characteristic information for extracting input picture sets up object module;
S3:Input video is read, and background model is set up with mixed Gauss model according to the input video, it is each to extract
Sport foreground in frame of video, and candidate target region is obtained by connected domain detection, utilized in the candidate target region
The edge contour estimation technique obtains all objects target frame position, and wherein object target frame refers to the rectangle for including edge closure object
Frame, obtains all objects target frame position step as follows using the edge contour estimation technique:A. the gradient map of target image is calculated;b.
Gradient map is subjected to multiple dimensioned scaling, the gradient map under different scale is obtained;C. the rectangle frame using yardstick as 4*4 travels through each
Gradient map, each pixel from the rectangle frame four edges of the gradient map is with perpendicular to the direction on the side, meter respectively
Calculation runs into first distance for being more than 64 Grad (i.e. marginal point), if finding marginal point from each pixel on each side
Distance average be less than 4, then judge that the rectangle frame corresponds to the rectangle frame of artwork as object target frame by scaling;
S4:By the characteristic similarity of the object target frame with search target in candidate target region with maximum comprehensive similarity
As the corresponding similarity of candidate target region, if the comprehensive similarity of candidate target region and search target is locked more than threshold value
The target;
S5:Indicated to each containing the frame of video for following the trail of target, sort out its temporal information, the type of lock onto target, lock
The characteristic information and the movable information of lock onto target set the goal, and these information are stored, Put on file sets up database;
S6:Needed to contrast the information in database according to user, filter out and follow the trail of the number that target position information is changed
According to result is fed back to user by integration frame of video resource.
The monitor video target lock-on tracing system and track lock method of the present invention has saved the time of artificial examination, carries
The high efficiency and accuracy of track lock, with higher practical value and widely application prospect.
It is obvious to a person skilled in the art that the invention is not restricted to the details of above-mentioned one exemplary embodiment, Er Qie
In the case of without departing substantially from spirit or essential attributes of the invention, the present invention can be realized in other specific forms.Therefore, no matter
From the point of view of which point, embodiment all should be regarded as exemplary, and be nonrestrictive, the scope of the present invention is by appended power
Profit is required rather than described above is limited, it is intended that all in the implication and scope of the equivalency of claim by falling
Change is included in the present invention.Any reference in claim should not be considered as to the claim involved by limitation.
Moreover, it will be appreciated that although the present specification is described in terms of embodiments, not each embodiment is only wrapped
Containing an independent technical scheme, this narrating mode of specification is only that for clarity, those skilled in the art should
Using specification as an entirety, the technical solutions in the various embodiments may also be suitably combined, forms those skilled in the art
It may be appreciated other embodiment.
Claims (8)
1. a kind of monitor video target lock-on tracing system, it is characterised in that including:
Target image characteristics stuck-module, the characteristic information for obtaining target image sets up object module;
Locking module is detected, is connected with the target image characteristics stuck-module, target is carried out for the video image to input
Detection, locks the object for meeting the object module that the target image characteristics stuck-module is set up in the video image, that is, needs
The moving target to be followed the trail of;
Tracing module, is connected with the detection locking module, after the detection locking module captures the moving target, knows
Not and follow the trail of the moving target, return to inactive state until detecting the moving target, stop following the trail of the motion mesh
Mark;
Target information analysis and arrangement module, is connected with the tracing module, and the relevant information of lock onto target is gone out for analysis and arrangement,
Video image frame sequence information, the type of lock onto target, the characteristic information of lock onto target and locking including the lock onto target
The movable information of target;
Data memory module, with the target image characteristics stuck-module, target information analysis and arrangement module, tracing module, inspection
Survey locking module to be connected, the relevant information for preserving the lock onto target that analysis and arrangement goes out sets up database;
As a result feedback module, is connected with data memory module, for carrying out classification screening to the information in database, to reduce
The number of times that repeats of lock onto target relevant information described in continuous time section internal lock in the selection result, and by final object information
Send user to.
2. monitor video target lock-on tracing system according to claim 1, it is characterised in that the spy of the target image
Reference breath includes:HSV color histograms feature, marginal point number and area ratio feature, perception Hash fingerprint characteristic.
3. monitor video target lock-on tracing system according to claim 1, it is characterised in that the video frame image sequence
Column information includes video image temporal information and image frame identification.
4. monitor video target lock-on tracing system according to claim 1, it is characterised in that the system also includes regarding
The real-time display module of frequency, the real-time display module of video is connected with the detection locking module, for according to the video figure
As frame sequence information extracts one or more image, or one or more snippets video from video, extraction is then shown in real time
Image or play extract video.
5. a kind of track lock side of monitor video target lock-on tracing system according to claim 1-4 any one
Method, it is characterised in that comprise the following steps:
(1)User inputs target image, and the characteristic information for extracting input picture sets up object module;
(2)Input video is read, and background model is set up according to the input video, to extract before the motion in each frame of video
Scape, and candidate target region is obtained by connected domain detection, asked in the candidate target region using the edge contour estimation technique
Go out all objects target frame position, wherein object target frame refers to the rectangle frame for including edge closure object;
(3)The characteristic similarity for having the object target frame of maximum comprehensive similarity with search target in candidate target region is made
For the corresponding similarity of candidate target region, it is somebody's turn to do if the comprehensive similarity of candidate target region and search target is more than threshold value locking
Target;
(4)Indicated to each containing the frame of video for following the trail of target, sort out its temporal information, the type of lock onto target, lock
The characteristic information and the movable information of lock onto target set the goal, and these information are stored, Put on file sets up database;
(5)Needed to contrast the information in database according to user, filter out and follow the trail of the number that target position information is changed
According to result is fed back to user by integration frame of video resource.
6. track lock method according to claim 5, it is characterised in that the step(1)Middle background model is using mixed
Close Gauss model.
7. track lock method according to claim 5, it is characterised in that the step(2)In in the candidate target
All objects target frame position is obtained in region using the edge contour estimation technique to comprise the following steps:A. the ladder of target image is calculated
Degree figure;B. gradient map is subjected to multiple dimensioned scaling, obtains the gradient map under different scale;C. using yardstick as 4*4 rectangle frame time
Each gradient map is gone through, is gone out respectively from each pixel on the rectangle frame four edges of the gradient map with the direction perpendicular to the side
Hair, calculates and runs into first distance for being more than 64 Grad (i.e. marginal point), if being found from each pixel on each side
The distance average of marginal point is less than 4, then judges that the rectangle frame corresponds to the rectangle frame of artwork as object mesh by scaling
Mark frame.
8. track lock method according to claim 5, it is characterised in that user needs to lead to before input track lock target
The searching system could be entered by crossing login account and password.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710217166.2A CN107103615A (en) | 2017-04-05 | 2017-04-05 | A kind of monitor video target lock-on tracing system and track lock method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710217166.2A CN107103615A (en) | 2017-04-05 | 2017-04-05 | A kind of monitor video target lock-on tracing system and track lock method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107103615A true CN107103615A (en) | 2017-08-29 |
Family
ID=59675704
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710217166.2A Withdrawn CN107103615A (en) | 2017-04-05 | 2017-04-05 | A kind of monitor video target lock-on tracing system and track lock method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107103615A (en) |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108377364A (en) * | 2018-02-07 | 2018-08-07 | 深圳市亿联智能有限公司 | A kind of high efficiency video monitoring mobile object trace mode |
CN110705476A (en) * | 2019-09-30 | 2020-01-17 | 深圳市商汤科技有限公司 | Data analysis method and device, electronic equipment and computer storage medium |
CN111382603A (en) * | 2018-12-28 | 2020-07-07 | 顺丰科技有限公司 | Track calculation device and method |
CN111476179A (en) * | 2020-04-10 | 2020-07-31 | 深圳市五元科技有限公司 | Behavior prediction method for key target, AI tracking camera and storage medium |
CN111523397A (en) * | 2020-03-31 | 2020-08-11 | 深圳市奥拓电子股份有限公司 | Intelligent lamp pole visual identification device, method and system and electronic equipment |
CN111784741A (en) * | 2020-06-29 | 2020-10-16 | 杭州海康威视数字技术股份有限公司 | Method and system for target cross-mirror distribution control tracking |
CN112422909A (en) * | 2020-11-09 | 2021-02-26 | 安徽数据堂科技有限公司 | Video behavior analysis management system based on artificial intelligence |
CN113781524A (en) * | 2021-09-13 | 2021-12-10 | 上海磐启微电子有限公司 | Target tracking system and method based on two-dimensional label |
CN113837171A (en) * | 2021-11-26 | 2021-12-24 | 成都数之联科技有限公司 | Candidate region extraction method, candidate region extraction system, candidate region extraction device, medium and target detection method |
CN112633145B (en) * | 2020-12-21 | 2024-04-26 | 武汉虚世科技有限公司 | WebAR processing method based on 3D detection recognition and moving target tracking |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101299812A (en) * | 2008-06-25 | 2008-11-05 | 北京中星微电子有限公司 | Method, system for analyzing, storing video as well as method, system for searching video |
CN101339664A (en) * | 2008-08-27 | 2009-01-07 | 北京中星微电子有限公司 | Object tracking method and system |
CN104866616A (en) * | 2015-06-07 | 2015-08-26 | 中科院成都信息技术股份有限公司 | Method for searching monitor video target |
-
2017
- 2017-04-05 CN CN201710217166.2A patent/CN107103615A/en not_active Withdrawn
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101299812A (en) * | 2008-06-25 | 2008-11-05 | 北京中星微电子有限公司 | Method, system for analyzing, storing video as well as method, system for searching video |
CN101339664A (en) * | 2008-08-27 | 2009-01-07 | 北京中星微电子有限公司 | Object tracking method and system |
CN104866616A (en) * | 2015-06-07 | 2015-08-26 | 中科院成都信息技术股份有限公司 | Method for searching monitor video target |
Cited By (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108377364A (en) * | 2018-02-07 | 2018-08-07 | 深圳市亿联智能有限公司 | A kind of high efficiency video monitoring mobile object trace mode |
CN108377364B (en) * | 2018-02-07 | 2020-09-01 | 深圳市亿联智能有限公司 | High-efficiency video monitoring moving object tracking mode |
CN111382603A (en) * | 2018-12-28 | 2020-07-07 | 顺丰科技有限公司 | Track calculation device and method |
CN111382603B (en) * | 2018-12-28 | 2023-09-26 | 顺丰科技有限公司 | Track calculation device and method |
CN110705476A (en) * | 2019-09-30 | 2020-01-17 | 深圳市商汤科技有限公司 | Data analysis method and device, electronic equipment and computer storage medium |
CN111523397B (en) * | 2020-03-31 | 2023-11-24 | 深圳市奥拓电子股份有限公司 | Intelligent lamp post visual identification device, method and system and electronic equipment thereof |
CN111523397A (en) * | 2020-03-31 | 2020-08-11 | 深圳市奥拓电子股份有限公司 | Intelligent lamp pole visual identification device, method and system and electronic equipment |
CN111476179B (en) * | 2020-04-10 | 2023-02-14 | 深圳市五元科技有限公司 | Behavior prediction method for key target, AI tracking camera and storage medium |
CN111476179A (en) * | 2020-04-10 | 2020-07-31 | 深圳市五元科技有限公司 | Behavior prediction method for key target, AI tracking camera and storage medium |
CN111784741A (en) * | 2020-06-29 | 2020-10-16 | 杭州海康威视数字技术股份有限公司 | Method and system for target cross-mirror distribution control tracking |
CN111784741B (en) * | 2020-06-29 | 2024-03-29 | 杭州海康威视数字技术股份有限公司 | Method and system for target cross-mirror distributed tracking |
CN112422909B (en) * | 2020-11-09 | 2022-10-14 | 安徽数据堂科技有限公司 | Video behavior analysis management system based on artificial intelligence |
CN112422909A (en) * | 2020-11-09 | 2021-02-26 | 安徽数据堂科技有限公司 | Video behavior analysis management system based on artificial intelligence |
CN112633145B (en) * | 2020-12-21 | 2024-04-26 | 武汉虚世科技有限公司 | WebAR processing method based on 3D detection recognition and moving target tracking |
CN113781524A (en) * | 2021-09-13 | 2021-12-10 | 上海磐启微电子有限公司 | Target tracking system and method based on two-dimensional label |
CN113781524B (en) * | 2021-09-13 | 2023-12-08 | 上海磐启微电子有限公司 | Target tracking system and method based on two-dimensional label |
CN113837171A (en) * | 2021-11-26 | 2021-12-24 | 成都数之联科技有限公司 | Candidate region extraction method, candidate region extraction system, candidate region extraction device, medium and target detection method |
CN113837171B (en) * | 2021-11-26 | 2022-02-08 | 成都数之联科技有限公司 | Candidate region extraction method, candidate region extraction system, candidate region extraction device, medium and target detection method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107103615A (en) | A kind of monitor video target lock-on tracing system and track lock method | |
CN107169106B (en) | Video retrieval method, device, storage medium and processor | |
CN102509118B (en) | Method for monitoring video retrieval | |
EP3566175A1 (en) | Systems and methods for behaviour understanding from trajectories | |
CN103714181B (en) | A kind of hierarchical particular persons search method | |
CN104376003B (en) | A kind of video retrieval method and device | |
CN102207966A (en) | Video content quick retrieving method based on object tag | |
CN105574506A (en) | Intelligent face tracking system and method based on depth learning and large-scale clustering | |
CN101848377B (en) | Device and method for intelligent linkage of multi-video recording device based on cloud computing and mass video searching | |
CN104978567B (en) | Vehicle checking method based on scene classification | |
Nguyen et al. | Anomaly detection in traffic surveillance videos with gan-based future frame prediction | |
Bianco et al. | Local detectors and compact descriptors for visual search: a quantitative comparison | |
CN107408119A (en) | Image retrieving apparatus, system and method | |
Zhong et al. | Dense moment feature index and best match algorithms for video copy-move forgery detection | |
CN104486585B (en) | A kind of city magnanimity monitor video management method and system based on GIS | |
CN103020606A (en) | Pedestrian detection method based on spatio-temporal context information | |
CN112541434B (en) | Face recognition method based on central point tracking model | |
Meng et al. | Descriptive temporal template features for visual motion recognition | |
Li et al. | End-to-end multiplayer violence detection based on deep 3D CNN | |
CN103187083B (en) | A kind of storage means based on time domain video fusion and system thereof | |
Di Benedetto et al. | An embedded toolset for human activity monitoring in critical environments | |
CN109684986A (en) | A kind of vehicle analysis method and system based on automobile detecting following | |
CN104504162B (en) | A kind of video retrieval method based on robot vision platform | |
CN106887014A (en) | A kind of pedestrian track matching process across camera | |
Mohammad et al. | Searching surveillance video contents using convolutional neural network |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20170829 |
|
WW01 | Invention patent application withdrawn after publication |